© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11612
    Prev
    Next
    INDEX
    Explanations

    the stem "rem" or "lim" followed by other characters or find "Am" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aan
    -0.74
    a
    -0.73
    able
    -0.68
    ae
    -0.65
    ab
    -0.64
    an
    -0.64
    aj
    -0.64
    ais
    -0.64
    ade
    -0.62
    ama
    -0.62
    POSITIVE LOGITS
    rolid
    0.49
    原始内容存档于
    0.45
     beginnetje
    0.45
    Assemblée
    0.43
    ishu
    0.42
    umpad
    0.42
    enquête
    0.42
    idex
    0.42
    wikidata
    0.42
    hygiène
    0.41
    Activations Density 3.286%

    No Known Activations